reference-data

Server Details

N American govt data, cited to source: rates, VAT, tax, wages, holidays, FX. 10 countries; USA free.

If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.

Status: Healthy
Uptime: 99.4% over 60 days
Last Tested: 2026-10-16 14:22
Transport: Streamable HTTP · MCP 2025-11-25
URL

TDQS

A4.1/5.0

Scored 2026-09-26 17:15 across 16 tools

Disambiguation5/5

Each tool addresses a distinct function: compliance checks, cost computations, series retrieval, calendar/holiday lookups, alerts, and receipt verification. No two tools overlap in purpose; even similar compute_* tools (VAT, income tax, employment cost) operate on clearly different inputs and outputs.

Naming Consistency4/5

Most tools follow a verb_noun pattern (compute_*, get_*, list_*, register_*, verify_*). Minor deviations include 'settlement_date' (noun phrase) and 'count_working_days' (count_* instead of compute_*), but these are readable and consistent with the domain's terminology.

Tool Count4/5

At 16 tools, the count is slightly above the typical well-scoped range, but each tool serves a necessary function for a legal/financial reference data server covering multiple countries and tax types. The breadth justifies the number without feeling bloated.

Completeness4/5

The tool surface covers core reference data operations: listing, retrieving current/historical/snapshot values, computing statutory obligations (VAT, income tax, employment cost, interest), working days and settlement dates, plus alerting and receipt verification. Minor gaps exist (e.g., no bulk export beyond snapshot, no currency conversion), but they don't hinder core workflows.

Available Tools

22 tools

add_business_daysAdd business days to a dateA

Read-onlyIdempotent

Inspect

FREE, unmetered. The date n business days after (or, for negative n, before) a start date. The start date is day 0 and never counted; n = 0 returns the date itself if it is a business day, otherwise the next one. Lists every non-business day skipped and why. Uses the country's national public-holiday calendar and its statutory weekend rule (Gulf Friday+Saturday, Israel Saturday-only, India 2nd/4th Saturdays, Nepal's 2026 change, China's multi-day breaks and make-up working days). A date in a year whose holidays we do not hold is refused with error year_not_held and the years_held list; it is never computed from weekends alone. A statutory holiday whose date is not yet fixed is refused as holiday_date_pending. Regional (sub-national) holidays are not applied.

ParametersJSON Schema

Name	Required	Description
`n`	Yes	Business days to add; negative walks backward
`date`	Yes	Start date (day 0), YYYY-MM-DD
`country`	Yes	ISO 3166-1 alpha-2 country code, e.g. 'za', 'ae', 'in'. Every country we hold a holiday calendar for is accepted on every brand, not only this brand's region.

Output Schema

ParametersJSON Schema

Name	Required	Description
`n`	No
`free`	No
`year`	No	On year_not_held: the year we do not hold
`basis`	No
`error`	No	Present on a free refusal or error; no charge
`price`	No
`caveats`	No
`country`	No
`reached`	No	On a refusal: the first date the calculation could not classify
`weekend`	No	Weekend days applied, the basis of that rule, and any dated or sub-national note
`calendar`	No	Holiday calendar used: years_held, source, last_confirmed, stale
`direction`	No
`no_charge`	No
`price_usd`	No
`convention`	No
`disclaimer`	No
`how_to_pay`	No
`start_date`	No
`years_held`	No	On year_not_held: the years whose holidays we do hold
`bind_series`	No
`explanation`	No
`result_date`	No
`x_next_bind`	No
`country_name`	No
`http_endpoint`	No
`result_weekday`	No
`what_you_can_do`	No
`payment_required`	No	true when the call needs payment; how_to_pay explains x402 or card
`calendar_days_moved`	No
`non_business_days_skipped`	No

TDQS

A4.4/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish read-only, idempotent, closed-world behavior, but the description goes well beyond them: it enumerates the country statutory weekend rules, discloses that regional holidays are NOT applied, and names two concrete refusal modes (year_not_held with years_held, holiday_date_pending). That is exactly the behavioral context an agent cannot get from structured fields alone.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the metering status and the core operation, then progressively narrows to edge cases, refusal modes, and exclusions. It is dense and multi-clause, but nearly every sentence carries a distinct rule an agent needs; only the parenthetical country-rule laundry list is slightly over-packed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return-shape details are correctly omitted, and the description still covers the failure modes, the calendar-coverage boundary, and the exclusions an agent must know to call this safely. Little is left for the agent to discover at runtime.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, and the description genuinely adds semantics beyond the schema: the start date is day 0 and never counted, n=0 returns the date itself if it is a business day else the next one, and negative n walks backward. The only gap is that the +/-500 bound and country-code format are left entirely to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Precise verb+resource: add N business days to a start date, with the direction (negative n walks backward) stated up front. This cleanly separates it from siblings like business_days_between, count_working_days, and is_business_day, which count or test rather than advance a date.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains the day-0 convention and the n=0 edge case, which implies the correct usage context, but it never explicitly names an alternative tool or states when to prefer this over business_days_between/count_working_days. Usage is inferable rather than routed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

business_days_betweenCount business days between two datesA

Read-onlyIdempotent

Inspect

FREE, unmetered. Business days between two dates. business_days counts (from, to] and is negative when to is before from, so add_business_days(from, business_days) lands on to whenever to is a business day; business_days_inclusive counts both ends. Also returns weekend days and the public holidays in range. Uses the country's national public-holiday calendar and its statutory weekend rule (Gulf Friday+Saturday, Israel Saturday-only, India 2nd/4th Saturdays, Nepal's 2026 change, China's multi-day breaks and make-up working days). A date in a year whose holidays we do not hold is refused with error year_not_held and the years_held list; it is never computed from weekends alone. A statutory holiday whose date is not yet fixed is refused as holiday_date_pending. Regional (sub-national) holidays are not applied.

ParametersJSON Schema

Name	Required	Description
`to`	Yes	Range end, YYYY-MM-DD
`from`	Yes	Range start, YYYY-MM-DD
`country`	Yes	ISO 3166-1 alpha-2 country code, e.g. 'za', 'ae', 'in'. Every country we hold a holiday calendar for is accepted on every brand, not only this brand's region.

Output Schema

ParametersJSON Schema

Name	Required	Description
`to`	No
`free`	No
`from`	No
`year`	No	On year_not_held: the year we do not hold
`basis`	No
`error`	No	Present on a free refusal or error; no charge
`price`	No
`caveats`	No
`country`	No
`reached`	No	On a refusal: the first date the calculation could not classify
`weekend`	No	Weekend days applied, the basis of that rule, and any dated or sub-national note
`calendar`	No	Holiday calendar used: years_held, source, last_confirmed, stale
`no_charge`	No
`price_usd`	No
`convention`	No
`disclaimer`	No
`how_to_pay`	No
`years_held`	No	On year_not_held: the years whose holidays we do hold
`bind_series`	No
`explanation`	No
`x_next_bind`	No
`country_name`	No
`weekend_days`	No
`business_days`	No	Business days in (from, to]; negative when to is before from
`http_endpoint`	No
`what_you_can_do`	No
`payment_required`	No	true when the call needs payment; how_to_pay explains x402 or card
`business_days_inclusive`	No	Business days counting both ends
`calendar_days_inclusive`	No
`public_holidays_on_weekdays`	No
`public_holidays_on_weekends`	No

TDQS

A4.7/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations, the description adds substantial behavioral detail: it is free and unmetered, defines the counting semantics including negative ranges, explains that weekend days and public holidays are returned, lists specific statutory weekend rules, and documents error behaviors such as year_not_held and holiday_date_pending. These are all meaningful operational traits not covered by the readOnly/idempotent annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose and key constraint, and most sentences are dense with useful detail. It is somewhat long and includes several illustrative country examples that, while relevant, could be trimmed for brevity, but the structure remains clear and purposeful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity and the existence of an output schema, the description is complete enough for correct invocation. It covers calculation semantics, return contents, calendar limitations, and explicit error conditions, leaving no significant ambiguity for an agent to resolve.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although schema coverage is already 100%, the description adds important semantic meaning: country selects a national public-holiday calendar and statutory weekend rule, from/to follow half-open interval semantics with potential negative counts, and regional holidays are excluded. This goes well beyond the schema's terse date and country-code descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a precise verb and resource: counting business days between two dates. It distinguishes itself from the sibling add_business_days by explaining the inverse relationship and the interval convention '(from, to]', and it clarifies the inclusive-counting variant, so an agent can identify the tool's exact purpose without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly explains when the tool is appropriate: counting business days between two dates while accounting for national holidays and statutory weekends. It also notes limitations such as regional holidays not being applied and errors for unsupported years, but it does not explicitly contrast with other date-related siblings like is_business_day or count_working_days.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

check_minimum_wage

Read-onlyIdempotent

Inspect

PAID ($0.05). Compliance verdict: is a salary at, above or below the country's statutory minimum wage? Returns verdict, margin, the statutory floor and the legal instrument it rests on. Honest statuses when no enforceable floor exists or the period doesn't match the floor's period (cross-period conversion is never guessed). Pass api_key if you have one (instant card checkout at /pricing); otherwise the response explains how to pay via x402. The evaluation country is free to try (see list_series). Optional receipt (boolean, default false): on a paid success, include an Ed25519 answer receipt at no extra USDC. An answer receipt is not a series certified extract (GET /v1/certified/{country}/{series} is $0.25 and is not an MCP tool) and is not legal advice. Verify with verify_answer_receipt against /certified/public-key.

ParametersJSON Schema

Name	Required	Description
`amount`	Yes	Wage to check, in the country's own currency
`period`	Yes	Period the amount covers — must match the statutory floor's period
`api_key`	No	API key (bypasses x402; metered for invoicing)
`country`	Yes	ISO country code
`receipt`	No	Default false. When true, a paid success includes an Ed25519 answer receipt (kind answer_receipt) at no extra USDC. Unpaid 402 and free refusals do not include one. Not a series certified extract (GET /v1/certified/{country}/{series} at $0.25; that SKU is not an MCP tool).

Output Schema

ParametersJSON Schema

Name	Required	Description
`basis`	No
`error`	No	Present on a free refusal or error; no charge
`floor`	No
`status`	No	Answer status, e.g. computed or an honest no-answer status
`country`	No
`receipt`	No	Ed25519 answer receipt when receipt=true on a paid success
`verdict`	No
`question`	No
`no_charge`	No
`price_usd`	No
`disclaimer`	No
`how_to_pay`	No
`provenance`	No	Cited official sources behind the answer
`bind_series`	No
`explanation`	No
`label_basis`	No	Inputs and the rule ids that produced the two labels
`x_next_bind`	No
`http_endpoint`	No
`coverage_label`	No	How much of the question is covered: ready = complete; partial = held with a disclosed limitation or default; gap = no number served. Rules at /label-rules
`confidence_label`	No	Evidence verdict derived from source type, verification age and the stale flag (answers: the weakest series read). Rules at /label-rules
`payment_required`	No	true when the call needs payment; how_to_pay explains x402 or card

compute_employment_cost

Read-onlyIdempotent

Inspect

PAID ($0.10). Cost to employ: prices every statutory contribution on both the employee and employer sides for a gross salary, returning line-by-line amounts with instrument citations and an explicit refused list for schemes that could not be priced (unknown, not zero). Does NOT compute income tax — use compute_payroll for gross-to-net take-home where supported. Pass api_key if you have one (instant card checkout at /pricing); otherwise the response explains how to pay via x402. The evaluation country is free to try (see list_series). Optional receipt (boolean, default false): on a paid success, include an Ed25519 answer receipt at no extra USDC. An answer receipt is not a series certified extract (GET /v1/certified/{country}/{series} is $0.25 and is not an MCP tool) and is not legal advice. Verify with verify_answer_receipt against /certified/public-key.

ParametersJSON Schema

Name	Required	Description
`gross`	Yes	Gross pay in local currency
`period`	No	Period the gross covers (default month)
`api_key`	No	API key (bypasses x402; metered for invoicing)
`country`	Yes	ISO country code with a costed contribution schedule
`receipt`	No	Default false. When true, a paid success includes an Ed25519 answer receipt (kind answer_receipt) at no extra USDC. Unpaid 402 and free refusals do not include one. Not a series certified extract (GET /v1/certified/{country}/{series} at $0.25; that SKU is not an MCP tool).
`contract`	No	Contract type where rates differ
`nationality`	No	Gulf nationality for pension reach
`subdivision`	No	Optional ISO 3166-2 regional schedule (e.g. CA-QC, DE-SN)
`childless_over_23`	No	Germany care surcharge
`children_under_25`	No	Germany per-child care reduction
`workplace_pension`	No	Auto-enrolment / PPK participation (default true)
`zusatzbeitrag_rate`	No	Germany sickness-fund supplement

Output Schema

ParametersJSON Schema

Name	Required	Description
`basis`	No
`error`	No	Present on a free refusal or error; no charge
`status`	No	Answer status, e.g. computed or an honest no-answer status
`country`	No
`receipt`	No	Ed25519 answer receipt when receipt=true on a paid success
`question`	No
`no_charge`	No
`price_usd`	No
`disclaimer`	No
`how_to_pay`	No
`provenance`	No	Cited official sources behind the answer
`bind_series`	No
`explanation`	No
`label_basis`	No	Inputs and the rule ids that produced the two labels
`x_next_bind`	No
`http_endpoint`	No
`coverage_label`	No	How much of the question is covered: ready = complete; partial = held with a disclosed limitation or default; gap = no number served. Rules at /label-rules
`confidence_label`	No	Evidence verdict derived from source type, verification age and the stale flag (answers: the weakest series read). Rules at /label-rules
`payment_required`	No	true when the call needs payment; how_to_pay explains x402 or card

compute_income_tax

Read-onlyIdempotent

Inspect

PAID ($0.05). Statutory income tax on a TAXABLE-income figure using the country's verified marginal bracket schedule, with full per-bracket workings, effective rate and marginal rate. You pass the amount in local currency. IMPORTANT: this is tax on taxable income, NOT net take-home pay — reliefs/allowances and social-security contributions are the caller's concern and are not applied (see the response scope_note). Pass api_key if you have one (instant card checkout at /pricing); otherwise the response explains how to pay via x402. The evaluation country is free to try (see list_series). Optional receipt (boolean, default false): on a paid success, include an Ed25519 answer receipt at no extra USDC. An answer receipt is not a series certified extract (GET /v1/certified/{country}/{series} is $0.25 and is not an MCP tool) and is not legal advice. Verify with verify_answer_receipt against /certified/public-key.

ParametersJSON Schema

Name	Required	Description
`api_key`	No	API key (bypasses x402; metered for invoicing)
`country`	Yes	ISO country code
`receipt`	No	Default false. When true, a paid success includes an Ed25519 answer receipt (kind answer_receipt) at no extra USDC. Unpaid 402 and free refusals do not include one. Not a series certified extract (GET /v1/certified/{country}/{series} at $0.25; that SKU is not an MCP tool).
`taxable_income`	Yes	Taxable income in the country's local currency, in the schedule's own period basis (annual for most; monthly for Côte d'Ivoire, Uganda, Ethiopia, Costa Rica)

Output Schema

ParametersJSON Schema

Name	Required	Description
`tax`	No
`basis`	No
`error`	No	Present on a free refusal or error; no charge
`status`	No	Answer status, e.g. computed or an honest no-answer status
`country`	No
`receipt`	No	Ed25519 answer receipt when receipt=true on a paid success
`question`	No
`breakdown`	No
`no_charge`	No
`price_usd`	No
`disclaimer`	No
`how_to_pay`	No
`provenance`	No	Cited official sources behind the answer
`scope_note`	No
`bind_series`	No
`explanation`	No
`label_basis`	No	Inputs and the rule ids that produced the two labels
`x_next_bind`	No
`http_endpoint`	No
`marginal_rate`	No
`coverage_label`	No	How much of the question is covered: ready = complete; partial = held with a disclosed limitation or default; gap = no number served. Rules at /label-rules
`effective_rate`	No
`confidence_label`	No	Evidence verdict derived from source type, verification age and the stale flag (answers: the weakest series read). Rules at /label-rules
`payment_required`	No	true when the call needs payment; how_to_pay explains x402 or card

compute_statutory_interest

Read-onlyIdempotent

Inspect

PAID ($0.05). Simple statutory interest on a principal at the cited statutory-interest series rate: Actual/365 simple, principal × (rate/100) × (days/365). Pass days, or from and to as YYYY-MM-DD (from inclusive, to exclusive). If both are sent and disagree, the call is refused free. A series with no numeric rate after materialization (mechanism-only) is refused free — a non-answer is not sold. Not legal advice. Jurisdiction-specific compounding and day-count statutes are not applied. Pass api_key if you have one (instant card checkout at /pricing); otherwise the response explains how to pay via x402. Every US series is free to try. Optional receipt (boolean, default false): on a paid success, include an Ed25519 answer receipt at no extra USDC. An answer receipt is not a series certified extract (GET /v1/certified/{country}/{series} is $0.25 and is not an MCP tool) and is not legal advice. Verify with verify_answer_receipt against /certified/public-key.

ParametersJSON Schema

Name	Required	Description
`to`	No	Period end, YYYY-MM-DD, exclusive.
`days`	No	Day-count days. Omit when from and to are set. If both are sent and disagree, the answer is refused free (HTTP 400).
`from`	No	Period start, YYYY-MM-DD, inclusive. Pair with to. Day count is calendar days from inclusive to to exclusive (UTC dates).
`api_key`	No	API key (bypasses x402; metered for invoicing)
`country`	Yes	ISO country code
`receipt`	No	Default false. When true, a paid success includes an Ed25519 answer receipt (kind answer_receipt) at no extra USDC. Unpaid 402 and free refusals do not include one. Not a series certified extract (GET /v1/certified/{country}/{series} at $0.25; that SKU is not an MCP tool).
`principal`	Yes	Principal in the country's own currency. Must be a finite number greater than 0.

Output Schema

ParametersJSON Schema

Name	Required	Description
`basis`	No
`error`	No	Present on a free refusal or error; no charge
`status`	No	Answer status, e.g. computed or an honest no-answer status
`country`	No
`receipt`	No	Ed25519 answer receipt when receipt=true on a paid success
`question`	No
`no_charge`	No
`price_usd`	No
`disclaimer`	No
`how_to_pay`	No
`provenance`	No	Cited official sources behind the answer
`bind_series`	No
`explanation`	No
`label_basis`	No	Inputs and the rule ids that produced the two labels
`x_next_bind`	No
`http_endpoint`	No
`coverage_label`	No	How much of the question is covered: ready = complete; partial = held with a disclosed limitation or default; gap = no number served. Rules at /label-rules
`confidence_label`	No	Evidence verdict derived from source type, verification age and the stale flag (answers: the weakest series read). Rules at /label-rules
`payment_required`	No	true when the call needs payment; how_to_pay explains x402 or card

compute_vat

Read-onlyIdempotent

Inspect

PAID ($0.02). VAT breakdown for an amount: net, tax and gross using the country's current statutory rate, including per-levy components where the rate is composite (e.g. Ghana VAT + NHIL + GETFund). mode=add treats the amount as net; mode=extract backs VAT out of a gross amount. Pass api_key if you have one (instant card checkout at /pricing); otherwise the response explains how to pay via x402. The evaluation country is free to try (see list_series). Optional receipt (boolean, default false): on a paid success, include an Ed25519 answer receipt at no extra USDC. An answer receipt is not a series certified extract (GET /v1/certified/{country}/{series} is $0.25 and is not an MCP tool) and is not legal advice. Verify with verify_answer_receipt against /certified/public-key.

ParametersJSON Schema

Name	Required	Description
`mode`	No	add = amount is net (default); extract = amount is gross
`amount`	Yes	Amount in the country's own currency
`api_key`	No	API key
`country`	Yes	ISO country code
`receipt`	No	Default false. When true, a paid success includes an Ed25519 answer receipt (kind answer_receipt) at no extra USDC. Unpaid 402 and free refusals do not include one. Not a series certified extract (GET /v1/certified/{country}/{series} at $0.25; that SKU is not an MCP tool).

Output Schema

ParametersJSON Schema

Name	Required	Description
`net`	No
`tax`	No
`rate`	No
`basis`	No
`error`	No	Present on a free refusal or error; no charge
`gross`	No
`status`	No	Answer status, e.g. computed or an honest no-answer status
`country`	No
`receipt`	No	Ed25519 answer receipt when receipt=true on a paid success
`question`	No
`workings`	No
`no_charge`	No
`price_usd`	No
`disclaimer`	No
`how_to_pay`	No
`provenance`	No	Cited official sources behind the answer
`bind_series`	No
`explanation`	No
`label_basis`	No	Inputs and the rule ids that produced the two labels
`x_next_bind`	No
`http_endpoint`	No
`coverage_label`	No	How much of the question is covered: ready = complete; partial = held with a disclosed limitation or default; gap = no number served. Rules at /label-rules
`confidence_label`	No	Evidence verdict derived from source type, verification age and the stale flag (answers: the weakest series read). Rules at /label-rules
`payment_required`	No	true when the call needs payment; how_to_pay explains x402 or card

count_working_days

Read-onlyIdempotent

Inspect

PAID ($0.02). Working days in a date range for a country: weekends (Egypt's Fri–Sat handled) and statutory public holidays applied, with the holidays hit by name and the next working day after the range. Range max 366 days. Pass api_key if you have one (instant card checkout at /pricing); otherwise the response explains how to pay via x402. The evaluation country is free to try (see list_series). Optional receipt (boolean, default false): on a paid success, include an Ed25519 answer receipt at no extra USDC. An answer receipt is not a series certified extract (GET /v1/certified/{country}/{series} is $0.25 and is not an MCP tool) and is not legal advice. Verify with verify_answer_receipt against /certified/public-key.

ParametersJSON Schema

Name	Required	Description
`to`	Yes	Range end, YYYY-MM-DD, inclusive
`from`	Yes	Range start, YYYY-MM-DD, inclusive
`api_key`	No	API key
`country`	Yes	ISO country code
`receipt`	No	Default false. When true, a paid success includes an Ed25519 answer receipt (kind answer_receipt) at no extra USDC. Unpaid 402 and free refusals do not include one. Not a series certified extract (GET /v1/certified/{country}/{series} at $0.25; that SKU is not an MCP tool).
`subdivision`	No	Optional ISO 3166-2 region code (e.g. 'DE-BY') to apply that region's statutory holidays on top of the national calendar. Regions are listed under `subdivisions` by get_public_holidays. Unknown code is refused free with the list.

Output Schema

ParametersJSON Schema

Name	Required	Description
`basis`	No
`error`	No	Present on a free refusal or error; no charge
`status`	No	Answer status, e.g. computed or an honest no-answer status
`country`	No
`receipt`	No	Ed25519 answer receipt when receipt=true on a paid success
`question`	No
`no_charge`	No
`price_usd`	No
`disclaimer`	No
`how_to_pay`	No
`provenance`	No	Cited official sources behind the answer
`bind_series`	No
`explanation`	No
`label_basis`	No	Inputs and the rule ids that produced the two labels
`x_next_bind`	No
`http_endpoint`	No
`coverage_label`	No	How much of the question is covered: ready = complete; partial = held with a disclosed limitation or default; gap = no number served. Rules at /label-rules
`confidence_label`	No	Evidence verdict derived from source type, verification age and the stale flag (answers: the weakest series read). Rules at /label-rules
`payment_required`	No	true when the call needs payment; how_to_pay explains x402 or card

get_calendar

Read-onlyIdempotent

Inspect

FREE, unmetered. GET /v1/calendar for this brand's continent. Optional country (ISO 3166-1 alpha-2) and series. Derives reverify_by from last_confirmed + update_cycle_days (the same window that sets stale) and, only when current.effective_to is a non-empty string, next_effective_known with basis effective_to. status unknown omits that date. Never parses notes. Does not invent MPC, budget, or wage-review dates. next_effective_known is the recorded end of the current value, not a promised gazette event. A 402 is a gate bug — do not pay. Past changes stay on get_changes.

ParametersJSON Schema

Name	Required	Description	Default
`series`	No	Optional series id (for example policy-rate). Omit for every series. A valid country with no match stays free.
`country`	No	Optional ISO 3166-1 alpha-2. Omit for every series on this brand's continent. Unknown to the catalog is 404 free. Not two letters is 400 free.

Output Schema

ParametersJSON Schema

Name	Required	Description
`as_of`	No
`brand`	No
`count`	No
`error`	No	Present on a free refusal or error; no charge
`entries`	No
`no_charge`	No
`price_usd`	No
`disclaimer`	No
`how_to_pay`	No
`bind_series`	No
`explanation`	No
`x_next_bind`	No
`http_endpoint`	No
`payment_required`	No	true when the call needs payment; how_to_pay explains x402 or card

get_changes

Read-onlyIdempotent

Inspect

FREE unmetered change + freshness feed. After any paid series or answer call, call this before you assume the cached value is still the law. Returns every series whose current value took effect on or after since (default last 30 days), newest first, each with last_confirmed and stale, PLUS a dataset-wide freshness summary: how many of the served series were re-verified within 1/7/30/90 days, how many are past their window, and which single series has gone longest without a check. Freshness is checkable or it is marketing. Args: since? (YYYY-MM-DD). Do not re-pay get_series to discover a diff. For a push bind, use register_alert (Register: $0 · Delivery after trial: $0.10). For a filing freeze of the current value, GET /v1/certified/{country}/{series} ($0.25).

ParametersJSON Schema

Name	Required	Description	Default
`since`	No	YYYY-MM-DD. Omit for the server default (last 30 days). Free, unmetered.

Output Schema

ParametersJSON Schema

Name	Required	Description
`as_of`	No
`error`	No	Present on a free refusal or error; no charge
`since`	No
`changes`	No
`no_charge`	No
`price_usd`	No
`disclaimer`	No
`how_to_pay`	No
`bind_series`	No
`explanation`	No
`x_next_bind`	No
`http_endpoint`	No
`payment_required`	No	true when the call needs payment; how_to_pay explains x402 or card

get_filing_deadlinesStatutory filing deadlinesA

Read-onlyIdempotent

Inspect

PAID ($0.005, same as any series). Recurring statutory tax deadlines for a country — VAT/GST returns and payments, PAYE/payroll withholding remittances, corporate income tax returns and provisional/instalment payments — as RULES, each cited to the official source with the verbatim phrase that states it, plus the actual DUE DATES in a window, rolled for the country's weekend and national public holidays (every skipped day is listed). Where a rule's source does not say which way a weekend deadline moves, the date is flagged roll_unverified rather than guessed. Countries or taxes we could not verify are returned as a free coverage_gap with reasons, never invented. Pass year_end (MM-DD) to re-anchor corporate-tax rules on the company's own accounting year end. The HTML page /{country}/filing-deadlines shows the rules free. Every US series is free to try. After a 200, bind get_changes (free poll) or register_alert (HMAC push; Register: $0 · Delivery after trial: $0.10) on this series so a later gazette does not silently retire the value.

ParametersJSON Schema

Name	Required	Description
`to`	No	Window end, YYYY-MM-DD. Default from + 365 days; at most 400 days after from
`tax`	No	Only this tax's rules and dates
`from`	No	Window start, YYYY-MM-DD. Default today
`api_key`	No	API key (bypasses x402; metered for invoicing)
`country`	Yes	ISO country code
`year_end`	No	Company accounting year end, MM-DD (e.g. 06-30). Applies to rules marked year_end_variable

Output Schema

ParametersJSON Schema

Name	Required	Description
`gaps`	No
`unit`	No
`error`	No	Present on a free refusal or error; no charge
`notes`	No
`stale`	No
`value`	No	The rules. Each carries its own source {name, url, anchor} and last_confirmed
`series`	No
`source`	No
`status`	No	On a coverage gap: researched_no_verified_rule or not_yet_researched
`country`	No
`due_dates`	No	Computed occurrences in the window, sorted by due_date
`no_charge`	No
`price_usd`	No
`confidence`	No
`disclaimer`	No
`how_to_pay`	No
`bind_series`	No
`explanation`	No
`label_basis`	No	Inputs and the rule ids that produced the two labels
`x_next_bind`	No
`coverage_gaps`	No	Taxes in scope with no verified rule for this country, and why
`http_endpoint`	No
`coverage_label`	No	How much of the question is covered: ready = complete; partial = held with a disclosed limitation or default; gap = no number served. Rules at /label-rules
`effective_from`	No
`last_confirmed`	No
`confidence_label`	No	Evidence verdict derived from source type, verification age and the stale flag (answers: the weakest series read). Rules at /label-rules
`payment_required`	No	true when the call needs payment; how_to_pay explains x402 or card
`computed_disclaimer`	No

TDQS

A4.5/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds rich behavioral context beyond annotations: pricing ($0.005), roll behavior for weekends/holidays, roll_unverified flagging when the source is ambiguous, coverage_gap for unverifiable countries instead of invention, and post-200 binding guidance. Annotations only cover safety; the description carries the real behavioral load.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the resource and value, but the description is dense and runs through pricing, rules, due dates, roll verification, coverage gaps, year_end, free HTML, trial terms, and follow-up binding in one block. Several clauses (e.g., the pricing parenthetical and HMAC push detail) could be trimmed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Complete for a complex paid data tool: with an output schema present, return values need not be explained, and the description covers scope, pricing, roll logic, error handling (coverage_gap), parameter nuances, and lifecycle (bind get_changes/register_alert). Nothing an agent needs to invoke it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds meaning: year_end re-anchors year_end_variable corporate-tax rules, which explains a non-obvious parameter interaction. It also implies the from/to window semantics, though the schema already documents these.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource (recurring statutory tax deadlines) with scope broken out by tax type (VAT/GST, PAYE, CIT) as rules plus due dates. Clearly distinguishable from siblings like compute_vat or get_public_holidays, which are single-purpose calculators.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear context: it is a paid series, HTML version is free, US series free to try, and it directs the agent to bind get_changes or register_alert afterward. It does not explicitly compare when to call this vs compute_vat or compute_statutory_interest, but usage context is otherwise clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_key_balanceA

Read-onlyIdempotent

Inspect

FREE. Remaining allowance for an API key (free, card or metered): plan, quota, used, remaining, reset date and what the key covers. Never metered. Pass api_key, or send the key as the X-API-Key header on /mcp.

ParametersJSON Schema

Name	Required	Description	Default
`api_key`	No	API key. Optional when sent as the X-API-Key header on /mcp.

Output Schema

ParametersJSON Schema

Name	Required	Description
`plan`	No
`used`	No
`error`	No	Present on a free refusal or error; no charge
`quota`	No
`covers`	No
`no_charge`	No
`price_usd`	No
`remaining`	No
`resets_on`	No
`disclaimer`	No
`how_to_pay`	No
`bind_series`	No
`explanation`	No
`x_next_bind`	No
`http_endpoint`	No
`payment_required`	No	true when the call needs payment; how_to_pay explains x402 or card

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and openWorld. The description adds real value beyond them: the pricing behavior ('FREE', 'Never metered') and the dual auth path. It does not mention pagination or error behavior, but with an output schema present the return shape is covered.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense but front-loaded: cost and return contents come first, then auth mechanics. Every phrase carries information, though the parenthetical '(free, card or metered)' packs three concepts into a fragment that reads slightly telegraphically.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Complete for a zero-required-parameter, single-purpose read tool: it covers cost, return fields, plan/coverage semantics, and both authentication paths, while the output schema handles return structure. An agent has everything needed to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the schema already explains api_key is optional when sent as a header. The description reinforces this by stating the alternative header mechanism explicitly, adding marginal convenience rather than new semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource (get key balance) and enumerates exactly what is returned: plan, quota, used, remaining, reset date, coverage. No sibling tool overlaps this domain, and the name alone would be ambiguous without this detail.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says 'FREE' and 'Never metered', telling the agent this is a no-cost, non-billing call, and explains the two calling conventions (api_key param or X-API-Key header). It stops short of naming alternatives or when-not-to-call, but for a one-purpose utility tool there is little ambiguity.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_public_holidays

Read-onlyIdempotent

Inspect

FREE. Official public-holiday calendar for a supported country, including gazetted movable holidays, with the official government source cited. Some countries also carry sub-national calendars (e.g. the German Laender): the subdivisions field lists them, and passing subdivision (ISO 3166-2, e.g. 'DE-BY') returns the national calendar merged with that region's statutory days.

ParametersJSON Schema

Name	Required	Description	Default
`country`	Yes	ISO country code
`subdivision`	No	Optional ISO 3166-2 region code (e.g. 'DE-BY'). Returns national + that region's statutory holidays, each tagged national/regional. Omit for the national calendar.

Output Schema

ParametersJSON Schema

Name	Required	Description
`unit`	No
`error`	No	Present on a free refusal or error; no charge
`notes`	No
`stale`	No
`value`	No
`series`	No
`source`	No
`country`	No
`no_charge`	No
`price_usd`	No
`confidence`	No
`disclaimer`	No
`how_to_pay`	No
`bind_series`	No
`explanation`	No
`label_basis`	No	Inputs and the rule ids that produced the two labels
`subdivision`	No
`x_next_bind`	No
`http_endpoint`	No
`coverage_label`	No	How much of the question is covered: ready = complete; partial = held with a disclosed limitation or default; gap = no number served. Rules at /label-rules
`effective_from`	No
`last_confirmed`	No
`confidence_label`	No	Evidence verdict derived from source type, verification age and the stale flag (answers: the weakest series read). Rules at /label-rules
`payment_required`	No	true when the call needs payment; how_to_pay explains x402 or card
`available_subdivisions`	No

get_public_holidays_worldwideA

Read-onlyIdempotent

Inspect

FREE with any API key, including the free key by email (https://usaref.dev/free-key). Same as get_public_holidays, but for every country across all seven brands, not only North American. Unmetered: never counts against the key's allowance. Pass api_key, or send the key as the X-API-Key header on /mcp.

ParametersJSON Schema

Name	Required	Description
`api_key`	No	Any valid API key. Optional when the key is sent as the X-API-Key header on /mcp.
`country`	Yes	ISO country code, any covered country
`subdivision`	No	Optional ISO 3166-2 region code (e.g. 'DE-BY'). Returns national + that region's statutory holidays, each tagged national/regional. Omit for the national calendar.

Output Schema

ParametersJSON Schema

Name	Required	Description
`unit`	No
`error`	No	Present on a free refusal or error; no charge
`notes`	No
`stale`	No
`value`	No
`series`	No
`source`	No
`country`	No
`no_charge`	No
`price_usd`	No
`confidence`	No
`disclaimer`	No
`how_to_pay`	No
`bind_series`	No
`explanation`	No
`label_basis`	No	Inputs and the rule ids that produced the two labels
`subdivision`	No
`x_next_bind`	No
`http_endpoint`	No
`coverage_label`	No	How much of the question is covered: ready = complete; partial = held with a disclosed limitation or default; gap = no number served. Rules at /label-rules
`effective_from`	No
`last_confirmed`	No
`confidence_label`	No	Evidence verdict derived from source type, verification age and the stale flag (answers: the weakest series read). Rules at /label-rules
`payment_required`	No	true when the call needs payment; how_to_pay explains x402 or card
`available_subdivisions`	No

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so safety is covered. The description earns credit by adding cost and auth behavior beyond the annotations: 'FREE with any API key,' 'Unmetered: never counts against the key's allowance,' and the alternative X-API-Key header path. It does not describe rate limiting or response shape, but those gaps are minor against the quota/auth disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences with no filler. Slight weakness in front-loading: it opens with billing/promo content and a free-key URL rather than stating the core capability, and the actual function is only defined by reference to a sibling ('Same as get_public_holidays').

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no explanation, and annotations cover the safety profile; between schema and description, params and auth are fully covered. The only unaddressed phrase is the unexplained 'seven brands,' which slightly limits how confidently an agent can predict coverage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so country, subdivision, and api_key are already documented in the schema with enum coverage. The description's auth note ('or send the key as the X-API-Key header') duplicates what the api_key schema description already says, adding no new parameter meaning. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource (get public holidays) with explicit scope: 'every country across all seven brands, not only North American.' It directly anchors itself against the sibling get_public_holidays, so an agent can distinguish the two without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly names the alternative ('Same as get_public_holidays, but for every country... not only North American'), which tells the agent exactly when to pick this tool over its near-identical sibling. The workaround-free coverage claim ('not only North American') gives the exclusion condition implicitly but unambiguously.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_series

Read-onlyIdempotent

Inspect

PAID ($0.005). Current value of a reference series — e.g. series=policy-rate, vat, minimum-wage. Every value carries its official source citation, effective date, last-confirmed date and staleness flag. Pass api_key if you have one (instant card checkout at /pricing); otherwise the response explains how to pay via x402. Every US series is free to try. After a 200, bind get_changes (free poll) or register_alert (HMAC push; Register: $0 · Delivery after trial: $0.10) on this series so a later gazette does not silently retire the value.

ParametersJSON Schema

Name	Required	Description
`series`	Yes	Series id, e.g. policy-rate, vat, minimum-wage
`api_key`	No	API key (bypasses x402; metered for invoicing)
`country`	Yes	ISO country code

Output Schema

ParametersJSON Schema

Name	Required	Description
`unit`	No
`error`	No	Present on a free refusal or error; no charge
`notes`	No
`stale`	No
`value`	No
`series`	No
`source`	No
`country`	No
`no_charge`	No
`price_usd`	No
`confidence`	No
`disclaimer`	No
`how_to_pay`	No
`bind_series`	No
`explanation`	No
`label_basis`	No	Inputs and the rule ids that produced the two labels
`x_next_bind`	No
`http_endpoint`	No
`coverage_label`	No	How much of the question is covered: ready = complete; partial = held with a disclosed limitation or default; gap = no number served. Rules at /label-rules
`effective_from`	No
`last_confirmed`	No
`confidence_label`	No	Evidence verdict derived from source type, verification age and the stale flag (answers: the weakest series read). Rules at /label-rules
`payment_required`	No	true when the call needs payment; how_to_pay explains x402 or card

get_series_history

Read-onlyIdempotent

Inspect

PAID ($0.005). Historical values of a reference series with effective date ranges, optionally filtered by from/to (YYYY-MM-DD). Pass api_key if you have one (instant card checkout at /pricing); otherwise the response explains how to pay via x402. Every US series is free to try. After a 200, bind get_changes (free poll) or register_alert (HMAC push; Register: $0 · Delivery after trial: $0.10) on this series so a later gazette does not silently retire the value.

ParametersJSON Schema

Name	Required	Description
`to`	No	Latest effective date, YYYY-MM-DD
`from`	No	Earliest effective date, YYYY-MM-DD
`series`	Yes	Series id
`api_key`	No	API key
`country`	Yes	ISO country code

Output Schema

ParametersJSON Schema

Name	Required	Description
`error`	No	Present on a free refusal or error; no charge
`stale`	No
`series`	No
`country`	No
`entries`	No
`no_charge`	No
`price_usd`	No
`disclaimer`	No
`how_to_pay`	No
`bind_series`	No
`explanation`	No
`label_basis`	No	Inputs and the rule ids that produced the two labels
`x_next_bind`	No
`http_endpoint`	No
`coverage_label`	No	How much of the question is covered: ready = complete; partial = held with a disclosed limitation or default; gap = no number served. Rules at /label-rules
`confidence_label`	No	Evidence verdict derived from source type, verification age and the stale flag (answers: the weakest series read). Rules at /label-rules
`payment_required`	No	true when the call needs payment; how_to_pay explains x402 or card

get_snapshot

Read-onlyIdempotent

Inspect

PAID ($0.02). Snapshot of every series for every country in one call. Pass api_key if you have one (instant card checkout at /pricing); otherwise the response explains how to pay via x402. Every US series is free to try. After a 200, bind get_changes (free poll) or register_alert (HMAC push; Register: $0 · Delivery after trial: $0.10) on this series so a later gazette does not silently retire the value.

ParametersJSON Schema

Name	Required	Description	Default
`api_key`	No	API key

Output Schema

ParametersJSON Schema

Name	Required	Description
`error`	No	Present on a free refusal or error; no charge
`result`	No	One entry per country; every series value carries confidence_label, coverage_label and label_basis
`countries`	No
`no_charge`	No
`price_usd`	No
`disclaimer`	No
`how_to_pay`	No
`bind_series`	No
`explanation`	No
`x_next_bind`	No
`http_endpoint`	No
`payment_required`	No	true when the call needs payment; how_to_pay explains x402 or card

is_business_dayIs it a business day?A

Read-onlyIdempotent

Inspect

FREE, unmetered. Is this date a business day in this country? Returns is_business_day, the reason (weekend, public_holiday, makeup_workday…), the holiday names, and the next and previous business day. Uses the country's national public-holiday calendar and its statutory weekend rule (Gulf Friday+Saturday, Israel Saturday-only, India 2nd/4th Saturdays, Nepal's 2026 change, China's multi-day breaks and make-up working days). A date in a year whose holidays we do not hold is refused with error year_not_held and the years_held list; it is never computed from weekends alone. A statutory holiday whose date is not yet fixed is refused as holiday_date_pending. Regional (sub-national) holidays are not applied.

ParametersJSON Schema

Name	Required	Description	Default
`date`	Yes	Date to classify, YYYY-MM-DD
`country`	Yes	ISO 3166-1 alpha-2 country code, e.g. 'za', 'ae', 'in'. Every country we hold a holiday calendar for is accepted on every brand, not only this brand's region.

Output Schema

ParametersJSON Schema

Name	Required	Description
`date`	No
`free`	No
`year`	No	On year_not_held: the year we do not hold
`basis`	No
`error`	No	Present on a free refusal or error; no charge
`price`	No
`reason`	No
`caveats`	No
`country`	No
`reached`	No	On a refusal: the first date the calculation could not classify
`weekday`	No
`weekend`	No	Weekend days applied, the basis of that rule, and any dated or sub-national note
`calendar`	No	Holiday calendar used: years_held, source, last_confirmed, stale
`no_charge`	No
`price_usd`	No
`disclaimer`	No
`how_to_pay`	No
`years_held`	No	On year_not_held: the years whose holidays we do hold
`bind_series`	No
`explanation`	No
`x_next_bind`	No
`country_name`	No
`http_endpoint`	No
`is_weekend_day`	No
`is_business_day`	No
`public_holidays`	No
`what_you_can_do`	No
`payment_required`	No	true when the call needs payment; how_to_pay explains x402 or card
`next_business_day`	No	{date, weekday}, or date null with why_unknown when it falls outside the held calendar
`previous_business_day`	No

TDQS

A4.5/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description adds substantial behavior: the 'FREE, unmetered' cost signal, the refusal semantics (year_not_held with years_held, holiday_date_pending), the guarantee that results are never inferred from weekends alone, and the explicit exclusion of sub-national holidays. This is well beyond what structured fields convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the cost signal and the core question, followed by returns and then edge-case behavior; every clause carries operational information. The dense weekend-rule parenthetical is long but earns its place by pre-empting surprising classifications.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter classification tool with an output schema and full annotations, the description covers purpose, return shape, error/refusal paths, cost, and scope exclusions. Nothing an agent needs to call it correctly or interpret a refusal is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and both parameters (date YYYY-MM-DD, ISO alpha-2 country) are fully documented in the schema itself. The description reinforces the scope of 'country' (national calendar, accepted across brands) but adds no syntax or format detail beyond the schema, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

'Is this date a business day in this country?' is a precise verb+resource, and the stated single-date classification scope implicitly separates it from the range-based siblings (business_days_between, count_working_days, add_business_days). The return summary (reason code, holiday names, adjacent business days) makes the operation unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description sets clear usage boundaries — it explicitly says regional/supranational holidays are not applied, that unheld years are refused, and which weekend regimes apply, which tells an agent when the answer is authoritative. It does not, however, name an alternative sibling (e.g. get_public_holidays_worldwide or count_working_days) or state when to prefer them, so it stops short of full when/when-not routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_series

Read-onlyIdempotent

Inspect

FREE. Catalog of all usaref reference-data series: supported countries, series ids, descriptions, freshness metadata and per-series URLs. Call this first to discover what data exists. Paid answer tools accept receipt=true (included in the answer price, no extra USDC) and, on a paid success, return an Ed25519 answer receipt (kind answer_receipt). That receipt is not a series certified extract and is not legal advice. Series certified extracts are GET /v1/certified/{country}/{series} at $0.25 and are not an MCP tool. Verify a receipt with verify_answer_receipt (free, public key only) against /certified/public-key. get_changes is free. get_calendar is free. register_alert registration is free.

ParametersJSON Schema

Name	Required	Description	Default
`detail`	No	Default false. Without country, false returns a compact index (country -> series ids). true returns the full catalog, which is large.
`country`	No	Optional ISO country code. Returns full per-series metadata (source, freshness, bands) for that country only.

Output Schema

ParametersJSON Schema

Name	Required	Description
`note`	No
`error`	No	Present on a free refusal or error; no charge
`countries`	No	Country entries ({country, name, series}); on an unknown-country refusal, the list of valid codes
`no_charge`	No
`price_usd`	No
`disclaimer`	No
`how_to_pay`	No
`bind_series`	No
`explanation`	No
`x_next_bind`	No
`http_endpoint`	No
`payment_required`	No	true when the call needs payment; how_to_pay explains x402 or card

register_alertInspect

Bind a webhook so the next gazette does not silently stale a value you already paid for. REGISTERING IS FREE. Register: $0 · Delivery after trial: $0.10. First 3 deliveries are free; later deliveries are $0.10 and refunded if the webhook fails to send. HMAC-SHA256 signed. Two watch types on the same call: • series: ["za/vat-registration-threshold", "ke/", ""] → series.changed when the served value or its effective date moves. On usaref those watches are statutory (minimum-wage, income-tax, statutory-interest, sales-tax, public-holidays), not a FRED-macro subscription. • sources: [""] → source.changed when the document BYTES change (old/new sha256 + citing series). Bytes ≠ value. Value changes arrive as series.changed. Unknown URLs refuse free (source_not_fingerprinted). Max 20 series + 20 sources. Required: url. Optional: api_key stored on the subscription to fund deliveries after the trial. This call does not meter that key. Prefer this over polling get_changes if you are a long-running agent. This is retention, not a new data product.

ParametersJSON Schema

Name	Required	Description
`url`	Yes	Webhook endpoint that will receive HMAC-SHA256 signed events
`series`	No	Value watches, e.g. ["za/vat-registration-threshold", "ke/", ""]
`api_key`	No	Optional prepaid key stored on the subscription to fund deliveries after the trial. This call does not meter it.
`sources`	No	Exact official-source URLs from a series source.url. Unknown URLs are refused free.

Output Schema

ParametersJSON Schema

Name	Required	Description
`error`	No	Present on a free refusal or error; no charge
`no_charge`	No
`price_usd`	No
`disclaimer`	No
`how_to_pay`	No
`bind_series`	No
`explanation`	No
`x_next_bind`	No
`http_endpoint`	No
`payment_required`	No	true when the call needs payment; how_to_pay explains x402 or card

settlement_date

Read-onlyIdempotent

Inspect

PAID ($0.05). Settlement/value date: the date n business days after a trade date, computed on the INTERSECTION of the calendars you name, with a per-day trail showing every skipped day and why, on which calendar. Supply business_days for a cycle you are trading under, or market + instrument_class to have a settlement cycle applied that we cite to its primary source (e.g. US equities T+1 under 17 CFR 240.15c6-1(a); UK gilts T+1 by DMO convention, which is NOT the T+2 equity cycle; Japan equities T+2 but JGBs T+1). Calendars are NATIONAL statutory holiday calendars with researched statutory weekend rules (Israel Saturday-only, Gulf Friday+Saturday, India Sundays plus the 2nd and 4th Saturday), NOT CSD or exchange calendars — each response states the basis and any known divergence. Use 'eu.t2' for the euro cash leg. We refuse FREE rather than guess: beyond published calendar coverage, no cited cycle for the instrument (government bonds never inherit an equity cycle), a cycle not in force on the trade date, or FX spot value dates. Free companion: GET /settlement-conventions. Optional receipt (boolean, default false): on a paid success, include an Ed25519 answer receipt at no extra USDC. An answer receipt is not a series certified extract (GET /v1/certified/{country}/{series} is $0.25 and is not an MCP tool) and is not legal advice. Verify with verify_answer_receipt against /certified/public-key.

ParametersJSON Schema

Name	Required	Description
`market`	No	ISO country of the market whose cited cycle should apply (with instrument_class)
`api_key`	No	API key (bypasses x402; metered for invoicing)
`receipt`	No	Default false. When true, a paid success includes an Ed25519 answer receipt (kind answer_receipt) at no extra USDC. Unpaid 402 and free refusals do not include one. Not a series certified extract (GET /v1/certified/{country}/{series} at $0.25; that SKU is not an MCP tool).
`calendars`	Yes	Calendar ids to intersect: two-letter ISO country codes, plus 'eu.t2' for the euro cash leg
`trade_date`	Yes	Trade/reference date, YYYY-MM-DD. Day 0: never counted, never rolled.
`business_days`	No	The offset you are trading under (T+n)
`instrument_class`	No	Instrument class — a government bond never inherits an equity cycle

Output Schema

ParametersJSON Schema

Name	Required	Description
`basis`	No
`error`	No	Present on a free refusal or error; no charge
`status`	No	Answer status, e.g. computed or an honest no-answer status
`country`	No
`receipt`	No	Ed25519 answer receipt when receipt=true on a paid success
`question`	No
`no_charge`	No
`price_usd`	No
`disclaimer`	No
`how_to_pay`	No
`provenance`	No	Cited official sources behind the answer
`bind_series`	No
`explanation`	No
`label_basis`	No	Inputs and the rule ids that produced the two labels
`x_next_bind`	No
`http_endpoint`	No
`coverage_label`	No	How much of the question is covered: ready = complete; partial = held with a disclosed limitation or default; gap = no number served. Rules at /label-rules
`confidence_label`	No	Evidence verdict derived from source type, verification age and the stale flag (answers: the weakest series read). Rules at /label-rules
`payment_required`	No	true when the call needs payment; how_to_pay explains x402 or card

verify_answer_receipt

Read-onlyIdempotent

Inspect

FREE. Verify an answer receipt (kind answer_receipt) with the Ed25519 public key only. Pass the receipt object or its canonical JSON, signature_value when the signature is not inside the receipt, and public_key_pem to verify offline. If public_key_pem is omitted, the tool may GET signature.public_key (/certified/public-key) and read public_key_pem. Never send a private key. A valid signature shows this service issued that exact receipt. It does not turn the receipt into a series certified extract (GET /v1/certified/{country}/{series} at $0.25, not an MCP tool) and it is not legal advice. Same key and canonical-JSON rule as /certified/public-key.

ParametersJSON Schema

Name	Required	Description
`receipt`	Yes	Answer receipt object (signature may be nested) or the canonical JSON of that object. A canonical JSON string of the signed body (signature omitted) is accepted when signature_value is also passed.
`public_key_pem`	No	SPKI public key PEM from GET /certified/public-key (field public_key_pem). Required for offline verify. A private key PEM is refused.
`public_key_url`	No	Optional GET /certified/public-key URL used only when public_key_pem is omitted. Ignored when the PEM is present.
`signature_value`	No	Base64 Ed25519 signature. Required when the receipt object or JSON string does not already include signature.value. Overrides a nested signature when both are sent.

Output Schema

ParametersJSON Schema

Name	Required	Description
`ok`	No
`why`	No
`error`	No	Present on a free refusal or error; no charge
`no_charge`	No
`price_usd`	No
`disclaimer`	No
`how_to_pay`	No
`bind_series`	No
`explanation`	No
`x_next_bind`	No
`http_endpoint`	No
`payment_required`	No	true when the call needs payment; how_to_pay explains x402 or card

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

15 tool updatesOct 13, 2026

Changedcheck_minimum_wage3 fields changed

addedOutput schema / properties / confidence_label

Added value: +{
+  "description": "Evidence verdict derived from source type, verification age and the stale flag (answers: the weakest series read). Rules at /label-rules",
+  "enum": [
+    "high",
+    "medium",
+    "low"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / coverage_label

Added value: +{
+  "description": "How much of the question is covered: ready = complete; partial = held with a disclosed limitation or default; gap = no number served. Rules at /label-rules",
+  "enum": [
+    "ready",
+    "partial",
+    "gap"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / label_basis

Added value: +{
+  "additionalProperties": {},
+  "description": "Inputs and the rule ids that produced the two labels",
+  "properties": {
+    "confidence_reasons": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "coverage_reasons": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "inputs": {
+      "items": {},
+      "type": "array"
+    },
+    "rules": {
+      "type": "string"
+    },
+    "rules_version": {
+      "type": "string"
+    },
+    "source_type": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "stale": {
+      "type": "boolean"
+    },
+    "verification_age_days": {
+      "anyOf": [
+        {
+          "type": "number"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    }
+  },
+  "type": "object"
+}

Changedcompute_employment_cost3 fields changed

addedOutput schema / properties / confidence_label

Added value: +{
+  "description": "Evidence verdict derived from source type, verification age and the stale flag (answers: the weakest series read). Rules at /label-rules",
+  "enum": [
+    "high",
+    "medium",
+    "low"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / coverage_label

Added value: +{
+  "description": "How much of the question is covered: ready = complete; partial = held with a disclosed limitation or default; gap = no number served. Rules at /label-rules",
+  "enum": [
+    "ready",
+    "partial",
+    "gap"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / label_basis

Added value: +{
+  "additionalProperties": {},
+  "description": "Inputs and the rule ids that produced the two labels",
+  "properties": {
+    "confidence_reasons": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "coverage_reasons": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "inputs": {
+      "items": {},
+      "type": "array"
+    },
+    "rules": {
+      "type": "string"
+    },
+    "rules_version": {
+      "type": "string"
+    },
+    "source_type": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "stale": {
+      "type": "boolean"
+    },
+    "verification_age_days": {
+      "anyOf": [
+        {
+          "type": "number"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    }
+  },
+  "type": "object"
+}

Changedcompute_income_tax3 fields changed

addedOutput schema / properties / confidence_label

Added value: +{
+  "description": "Evidence verdict derived from source type, verification age and the stale flag (answers: the weakest series read). Rules at /label-rules",
+  "enum": [
+    "high",
+    "medium",
+    "low"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / coverage_label

Added value: +{
+  "description": "How much of the question is covered: ready = complete; partial = held with a disclosed limitation or default; gap = no number served. Rules at /label-rules",
+  "enum": [
+    "ready",
+    "partial",
+    "gap"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / label_basis

Added value: +{
+  "additionalProperties": {},
+  "description": "Inputs and the rule ids that produced the two labels",
+  "properties": {
+    "confidence_reasons": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "coverage_reasons": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "inputs": {
+      "items": {},
+      "type": "array"
+    },
+    "rules": {
+      "type": "string"
+    },
+    "rules_version": {
+      "type": "string"
+    },
+    "source_type": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "stale": {
+      "type": "boolean"
+    },
+    "verification_age_days": {
+      "anyOf": [
+        {
+          "type": "number"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    }
+  },
+  "type": "object"
+}

Changedcompute_statutory_interest3 fields changed

addedOutput schema / properties / confidence_label

Added value: +{
+  "description": "Evidence verdict derived from source type, verification age and the stale flag (answers: the weakest series read). Rules at /label-rules",
+  "enum": [
+    "high",
+    "medium",
+    "low"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / coverage_label

Added value: +{
+  "description": "How much of the question is covered: ready = complete; partial = held with a disclosed limitation or default; gap = no number served. Rules at /label-rules",
+  "enum": [
+    "ready",
+    "partial",
+    "gap"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / label_basis

Added value: +{
+  "additionalProperties": {},
+  "description": "Inputs and the rule ids that produced the two labels",
+  "properties": {
+    "confidence_reasons": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "coverage_reasons": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "inputs": {
+      "items": {},
+      "type": "array"
+    },
+    "rules": {
+      "type": "string"
+    },
+    "rules_version": {
+      "type": "string"
+    },
+    "source_type": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "stale": {
+      "type": "boolean"
+    },
+    "verification_age_days": {
+      "anyOf": [
+        {
+          "type": "number"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    }
+  },
+  "type": "object"
+}

Changedcompute_vat3 fields changed

addedOutput schema / properties / confidence_label

Added value: +{
+  "description": "Evidence verdict derived from source type, verification age and the stale flag (answers: the weakest series read). Rules at /label-rules",
+  "enum": [
+    "high",
+    "medium",
+    "low"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / coverage_label

Added value: +{
+  "description": "How much of the question is covered: ready = complete; partial = held with a disclosed limitation or default; gap = no number served. Rules at /label-rules",
+  "enum": [
+    "ready",
+    "partial",
+    "gap"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / label_basis

Added value: +{
+  "additionalProperties": {},
+  "description": "Inputs and the rule ids that produced the two labels",
+  "properties": {
+    "confidence_reasons": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "coverage_reasons": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "inputs": {
+      "items": {},
+      "type": "array"
+    },
+    "rules": {
+      "type": "string"
+    },
+    "rules_version": {
+      "type": "string"
+    },
+    "source_type": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "stale": {
+      "type": "boolean"
+    },
+    "verification_age_days": {
+      "anyOf": [
+        {
+          "type": "number"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    }
+  },
+  "type": "object"
+}

Changedcount_working_days3 fields changed

addedOutput schema / properties / confidence_label

Added value: +{
+  "description": "Evidence verdict derived from source type, verification age and the stale flag (answers: the weakest series read). Rules at /label-rules",
+  "enum": [
+    "high",
+    "medium",
+    "low"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / coverage_label

Added value: +{
+  "description": "How much of the question is covered: ready = complete; partial = held with a disclosed limitation or default; gap = no number served. Rules at /label-rules",
+  "enum": [
+    "ready",
+    "partial",
+    "gap"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / label_basis

Added value: +{
+  "additionalProperties": {},
+  "description": "Inputs and the rule ids that produced the two labels",
+  "properties": {
+    "confidence_reasons": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "coverage_reasons": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "inputs": {
+      "items": {},
+      "type": "array"
+    },
+    "rules": {
+      "type": "string"
+    },
+    "rules_version": {
+      "type": "string"
+    },
+    "source_type": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "stale": {
+      "type": "boolean"
+    },
+    "verification_age_days": {
+      "anyOf": [
+        {
+          "type": "number"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    }
+  },
+  "type": "object"
+}

Addedget_filing_deadlines
Addedget_key_balance

Changedget_public_holidays3 fields changed

addedOutput schema / properties / confidence_label

Added value: +{
+  "description": "Evidence verdict derived from source type, verification age and the stale flag (answers: the weakest series read). Rules at /label-rules",
+  "enum": [
+    "high",
+    "medium",
+    "low"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / coverage_label

Added value: +{
+  "description": "How much of the question is covered: ready = complete; partial = held with a disclosed limitation or default; gap = no number served. Rules at /label-rules",
+  "enum": [
+    "ready",
+    "partial",
+    "gap"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / label_basis

Added value: +{
+  "additionalProperties": {},
+  "description": "Inputs and the rule ids that produced the two labels",
+  "properties": {
+    "confidence_reasons": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "coverage_reasons": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "inputs": {
+      "items": {},
+      "type": "array"
+    },
+    "rules": {
+      "type": "string"
+    },
+    "rules_version": {
+      "type": "string"
+    },
+    "source_type": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "stale": {
+      "type": "boolean"
+    },
+    "verification_age_days": {
+      "anyOf": [
+        {
+          "type": "number"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    }
+  },
+  "type": "object"
+}

Addedget_public_holidays_worldwide

Changedget_series3 fields changed

addedOutput schema / properties / confidence_label

Added value: +{
+  "description": "Evidence verdict derived from source type, verification age and the stale flag (answers: the weakest series read). Rules at /label-rules",
+  "enum": [
+    "high",
+    "medium",
+    "low"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / coverage_label

Added value: +{
+  "description": "How much of the question is covered: ready = complete; partial = held with a disclosed limitation or default; gap = no number served. Rules at /label-rules",
+  "enum": [
+    "ready",
+    "partial",
+    "gap"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / label_basis

Added value: +{
+  "additionalProperties": {},
+  "description": "Inputs and the rule ids that produced the two labels",
+  "properties": {
+    "confidence_reasons": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "coverage_reasons": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "inputs": {
+      "items": {},
+      "type": "array"
+    },
+    "rules": {
+      "type": "string"
+    },
+    "rules_version": {
+      "type": "string"
+    },
+    "source_type": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "stale": {
+      "type": "boolean"
+    },
+    "verification_age_days": {
+      "anyOf": [
+        {
+          "type": "number"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    }
+  },
+  "type": "object"
+}

Changedget_series_history7 fields changed

changedOutput schema / description

Previous value: -"Historical entries of one series"New value: +"Historical entries of one series; top-level labels describe the current value, and each entry carries its own"

addedOutput schema / properties / confidence_label

Added value: +{
+  "description": "Evidence verdict derived from source type, verification age and the stale flag (answers: the weakest series read). Rules at /label-rules",
+  "enum": [
+    "high",
+    "medium",
+    "low"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / coverage_label

Added value: +{
+  "description": "How much of the question is covered: ready = complete; partial = held with a disclosed limitation or default; gap = no number served. Rules at /label-rules",
+  "enum": [
+    "ready",
+    "partial",
+    "gap"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / entries / items / additionalProperties
```
Added value: +{}
```

addedOutput schema / properties / entries / items / properties

Added value: +{
+  "confidence": {},
+  "confidence_label": {
+    "description": "Evidence verdict derived from source type, verification age and the stale flag (answers: the weakest series read). Rules at /label-rules",
+    "enum": [
+      "high",
+      "medium",
+      "low"
+    ],
+    "type": "string"
+  },
+  "country": {
+    "type": "string"
+  },
+  "coverage_label": {
+    "description": "How much of the question is covered: ready = complete; partial = held with a disclosed limitation or default; gap = no number served. Rules at /label-rules",
+    "enum": [
+      "ready",
+      "partial",
+      "gap"
+    ],
+    "type": "string"
+  },
+  "effective_from": {},
+  "label_basis": {
+    "additionalProperties": {},
+    "description": "Inputs and the rule ids that produced the two labels",
+    "properties": {
+      "confidence_reasons": {
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      "coverage_reasons": {
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      "inputs": {
+        "items": {},
+        "type": "array"
+      },
+      "rules": {
+        "type": "string"
+      },
+      "rules_version": {
+        "type": "string"
+      },
+      "source_type": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "stale": {
+        "type": "boolean"
+      },
+      "verification_age_days": {
+        "anyOf": [
+          {
+            "type": "number"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      }
+    },
+    "type": "object"
+  },
+  "last_confirmed": {},
+  "notes": {},
+  "series": {
+    "type": "string"
+  },
+  "source": {},
+  "stale": {
+    "type": "boolean"
+  },
+  "unit": {},
+  "value": {}
+}

addedOutput schema / properties / entries / items / type
```
Added value: +"object"
```

addedOutput schema / properties / label_basis

Added value: +{
+  "additionalProperties": {},
+  "description": "Inputs and the rule ids that produced the two labels",
+  "properties": {
+    "confidence_reasons": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "coverage_reasons": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "inputs": {
+      "items": {},
+      "type": "array"
+    },
+    "rules": {
+      "type": "string"
+    },
+    "rules_version": {
+      "type": "string"
+    },
+    "source_type": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "stale": {
+      "type": "boolean"
+    },
+    "verification_age_days": {
+      "anyOf": [
+        {
+          "type": "number"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    }
+  },
+  "type": "object"
+}

Changedget_snapshot1 field changed

addedOutput schema / properties / result

Added value: +{
+  "description": "One entry per country; every series value carries confidence_label, coverage_label and label_basis",
+  "items": {
+    "additionalProperties": {},
+    "properties": {
+      "country": {
+        "type": "string"
+      },
+      "series": {
+        "items": {
+          "additionalProperties": {},
+          "properties": {
+            "confidence": {},
+            "confidence_label": {
+              "description": "Evidence verdict derived from source type, verification age and the stale flag (answers: the weakest series read). Rules at /label-rules",
+              "enum": [
+                "high",
+                "medium",
+                "low"
+              ],
+              "type": "string"
+            },
+            "country": {
+              "type": "string"
+            },
+            "coverage_label": {
+              "description": "How much of the question is covered: ready = complete; partial = held with a disclosed limitation or default; gap = no number served. Rules at /label-rules",
+              "enum": [
+                "ready",
+                "partial",
+                "gap"
+              ],
+              "type": "string"
+            },
+            "effective_from": {},
+            "label_basis": {
+              "additionalProperties": {},
+              "description": "Inputs and the rule ids that produced the two labels",
+              "properties": {
+                "confidence_reasons": {
+                  "items": {
+                    "type": "string"
+                  },
+                  "type": "array"
+                },
+                "coverage_reasons": {
+                  "items": {
+                    "type": "string"
+                  },
+                  "type": "array"
+                },
+                "inputs": {
+                  "items": {},
+                  "type": "array"
+                },
+                "rules": {
+                  "type": "string"
+                },
+                "rules_version": {
+                  "type": "string"
+                },
+                "source_type": {
+                  "anyOf": [
+                    {
+                      "type": "string"
+                    },
+                    {
+                      "type": "null"
+                    }
+                  ]
+                },
+                "stale": {
+                  "type": "boolean"
+                },
+                "verification_age_days": {
+                  "anyOf": [
+                    {
+                      "type": "number"
+                    },
+                    {
+                      "type": "null"
+                    }
+                  ]
+                }
+              },
+              "type": "object"
+            },
+            "last_confirmed": {},
+            "notes": {},
+            "series": {
+              "type": "string"
+            },
+            "source": {},
+            "stale": {
+              "type": "boolean"
+            },
+            "unit": {},
+            "value": {}
+          },
+          "type": "object"
+        },
+        "type": "array"
+      }
+    },
+    "type": "object"
+  },
+  "type": "array"
+}

Changedlist_series1 field changed

changedOutput schema / description

Previous value: -"Catalog: brand metadata plus countries[] (compact: country, name, series ids; with country or detail: full per-series metadata)"New value: +"Catalog: brand metadata plus countries[] (compact: country, name, series ids; with country or detail: full per-series metadata including confidence_label and coverage_label)"

Changedsettlement_date3 fields changed

addedOutput schema / properties / confidence_label

Added value: +{
+  "description": "Evidence verdict derived from source type, verification age and the stale flag (answers: the weakest series read). Rules at /label-rules",
+  "enum": [
+    "high",
+    "medium",
+    "low"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / coverage_label

Added value: +{
+  "description": "How much of the question is covered: ready = complete; partial = held with a disclosed limitation or default; gap = no number served. Rules at /label-rules",
+  "enum": [
+    "ready",
+    "partial",
+    "gap"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / label_basis

Added value: +{
+  "additionalProperties": {},
+  "description": "Inputs and the rule ids that produced the two labels",
+  "properties": {
+    "confidence_reasons": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "coverage_reasons": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "inputs": {
+      "items": {},
+      "type": "array"
+    },
+    "rules": {
+      "type": "string"
+    },
+    "rules_version": {
+      "type": "string"
+    },
+    "source_type": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "stale": {
+      "type": "boolean"
+    },
+    "verification_age_days": {
+      "anyOf": [
+        {
+          "type": "number"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    }
+  },
+  "type": "object"
+}

3 tool updatesOct 13, 2026
- Addedadd_business_days
- Addedbusiness_days_between
- Addedis_business_day

16 tool updatesOct 12, 2026

Changedcheck_minimum_wage1 field changed